Daniel Lenton

Founder at Unify, where we're building neural routers to send each prompt to the best LLM.

LinkedIn  /  Twitter  /  Medium  /  Google Scholar  /  Email

Ivy enables the integration of code from one ML framework into another, speeding up development and also model inference.

ESM encodes the memory in an ego-sphere around the agent, enabling expressive 3D representations. ESM can be trained end-to-end via either imitation or reinforcement learning, and improves both training efficiency and final performance against other memory baselines on visuomotor control tasks.

We demonstrate that challenging shortest path problems can be solved via direct spline regression from a neural network, trained in an unsupervised manner without requiring ground truth optimal paths for training. To achieve this, we derive a geometry-dependent optimal cost function whose minima guarantees collision-free solutions.

Waypoint Planning Networks, or WPN, is a hybrid motion planning algorithm based on LSTMs with a local kernel, a classic algorithm such as A*, and a global kernel using a learned algorithm. WPN produces a more computationally efficient and robust solution than other learned approaches.

MoreFusion makes 3D object pose proposals from single RGB-D views, accumulates pose estimates and non-parametric occupancy information from multiple views as the camera moves, and performs joint optimization to estimate consistent, non-intersecting poses for multiple objects in contact.